@omegaengine/mcp

The trust & control layer for AI agents — as an MCP server.

Drop OmegaEngine into any Model Context Protocol client (Claude Desktop, Cursor, Windsurf, and the rest) and your agent can govern, red-team, and cryptographically verify every action — before it executes.

Proof, not promises. Every verdict OmegaEngine returns is signed and offline-verifiable. Don't trust your AI — verify it.

Tools

| Tool | What it does | |---|---| | check_action | Govern an action before it runs — scores risk, enforces your policy, returns a signed approved \| denied \| escalated verdict + a tamper-evident audit id. | | scan_agent | Red-team an agent's prompt + tools against the attack corpus (prompt injection, tool-call injection, data exfiltration, excessive agency). Returns the exploits found. | | verify_proof | Cryptographically verify a signed OmegaEngine decision — offline, without trusting OmegaEngine. |

Install

npx -y @omegaengine/mcp        # runs the server (stdio)

Claude Desktop / Cursor / Windsurf

Add to your MCP config (claude_desktop_config.json, Cursor mcp.json, etc.):

{
  "mcpServers": {
    "omega-engine": {
      "command": "npx",
      "args": ["-y", "@omegaengine/mcp"],
      "env": {
        "OMEGA_API_KEY": "your-omegaengine-api-key",
        "OMEGA_BASE_URL": "https://omegaengine.ai"
      }
    }
  }
}

• OMEGA_API_KEY — your OmegaEngine API key (get one free). Required for check_action. scan_agent (sample mode) and verify_proof work without it.
• OMEGA_BASE_URL — defaults to https://omegaengine.ai. Point it at your self-hosted instance (e.g. http://localhost:3000) to keep everything on-prem.

Example

Once connected, your agent can call:

check_action(agent_id="treasury-agent", action="wire_transfer", amount=50000, risk_level="high")
→ { "decision": "escalated", "risk_score": 82, "requires_human": true, "audit_id": "aud_7x8k2m9n…" }

scan_agent(system_prompt="You are a support agent…", tools=[…], openai_api_key="sk-…")
→ { "summary": { "exploited": 3, "worst": "critical" }, "results": [ … send_email→[email protected] … ] }

verify_proof(decision={…}, signature="omega-3190df…")
→ { "valid": true, "tampered": false }

Build from source

npm install && npm run build && node dist/index.js

Security

• The server is a thin client — the engine, audit trail, and signing live in OmegaEngine. No decision logic runs locally.
• scan_agent's openai_api_key is used in-request only, never stored or logged.
• Diagnostics are written to stderr; stdout is reserved for the MCP transport.

Apache-2.0 · omegaengine.ai